文章基本信息

标题：A Mixed Approach for Hindi News Article Gist Generation
本地全文：下载
作者：M. Varaprasad Rao ; Dr. B. Vishnu Vardhan
期刊名称：International Journal of Advanced Research In Computer Science and Software Engineering
印刷版ISSN：2277-6451
电子版ISSN：2277-128X
出版年度：2013
卷号：3
期号：8
出版社：S.S. Mishra
摘要：Huge news articles are reported and disseminated on the Internet. How to extract key information and save the reading time is the important issue. Gist is often used to summarize the content of the document. In this paper improved statistical approa ch based on keywords is presented. Gist generation problem can be viewed as finding informative keywords from the document and finding the proper way to combine these words to reflect a coherent and grammatical phrase. To improve the accuracy of the key phrase in reflecting the content, the summary of the document is first identified. The results show that proposed approach is more suitable for generating informative key phrases. This paper identifies the informative words from the summary of the document. The results are evaluated using precision, recall and F1 measure
关键词：Text summarization; statistical model; F1 measure; key phrase